General model by squ11z1 · 8.97B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gpt oss nano fits comfortably in your 24 GB Mac using Q8_0 quantization, using 44% of your RAM.
— tok/s
Q8_0 · 10.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 10.5 GB | ~49 tok/s | ✓ |
| Q6_K | 8.3 GB | ~64 tok/s | ✓ |
| Q5_K_M | 7.2 GB | ~76 tok/s | ✓ |
| Q4_K_M | 6.3 GB | ~89 tok/s | ✓ |
| Q3_K_M | 5.4 GB | ~107 tok/s | ✓ |
| Q2_K | 4.4 GB | ~139 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free